English
Related papers

Related papers: Long-Horizon Q-Learning: Accurate Value Learning v…

200 papers

``Distribution shift'' is the main obstacle to the success of offline reinforcement learning. A learning policy may take actions beyond the behavior policy's knowledge, referred to as Out-of-Distribution (OOD) actions. The Q-values for…

Machine Learning · Computer Science 2025-01-14 Jing Zhang , Linjiajie Fang , Kexin Shi , Wenjia Wang , Bing-Yi Jing

Unsupervised pre-training has recently become the bedrock for computer vision and natural language processing. In reinforcement learning (RL), goal-conditioned RL can potentially provide an analogous self-supervised approach for making use…

Machine Learning · Computer Science 2024-03-12 Seohong Park , Dibya Ghosh , Benjamin Eysenbach , Sergey Levine

In classical Q-learning, the objective is to maximize the sum of discounted rewards through iteratively using the Bellman equation as an update, in an attempt to estimate the action value function of the optimal policy. Conventionally, the…

Machine Learning · Computer Science 2019-06-25 Hadi S. Jomaa , Josif Grabocka , Lars Schmidt-Thieme

Hierarchical goal-conditioned reinforcement learning (H-GCRL) provides a powerful framework for tackling complex, long-horizon tasks by decomposing them into structured subgoals. However, its practical adoption is hindered by poor data…

Robotics · Computer Science 2026-02-12 Shaswat Garg , Matin Moezzi , Brandon Da Silva

Value-based reinforcement learning (RL) methods like Q-learning have shown success in a variety of domains. One challenge in applying Q-learning to continuous-action RL problems, however, is the continuous action maximization (max-Q)…

Machine Learning · Computer Science 2020-03-03 Moonkyung Ryu , Yinlam Chow , Ross Anderson , Christian Tjandraatmadja , Craig Boutilier

Offline Reinforcement Learning (RL) faces a fundamental challenge of extrapolation errors caused by out-of-distribution (OOD) actions. Implicit Q-Learning (IQL) employs expectile regression to achieve in-sample learning. Nevertheless, IQL…

Machine Learning · Computer Science 2026-02-03 Xinchen Han , Hossam Afifi , Michel Marot

We study reinforcement learning in infinite-horizon discounted Markov decision processes with continuous state spaces, where data are generated online from a single trajectory under a Markovian behavior policy. To avoid maintaining an…

Machine Learning · Computer Science 2026-03-05 Shengbo Wang

In this paper, a deep reinforcement learning based method is proposed to obtain optimal policies for optimal infinite-horizon control of probabilistic Boolean control networks (PBCNs). Compared with the existing literatures, the proposed…

Systems and Control · Electrical Eng. & Systems 2023-04-10 Jingjie Ni , Fangfei Li , Zheng-Guang Wu

Reinforcement learning is time-consuming for complex tasks due to the need for large amounts of training data. Recent advances in GPU-based simulation, such as Isaac Gym, have sped up data collection thousands of times on a commodity GPU.…

Machine Learning · Computer Science 2023-07-25 Zechu Li , Tao Chen , Zhang-Wei Hong , Anurag Ajay , Pulkit Agrawal

This paper introduces an approach to Reinforcement Learning Algorithm by comparing their immediate rewards using a variation of Q-Learning algorithm. Unlike the conventional Q-Learning, the proposed algorithm compares current reward with…

Machine Learning · Computer Science 2010-09-15 Punit Pandey , Deepshikha Pandey , Shishir Kumar

Offline reinforcement learning (RL) tries to learn the near-optimal policy with recorded offline experience without online exploration. Current offline RL research includes: 1) generative modeling, i.e., approximating a policy using fixed…

Machine Learning · Computer Science 2021-06-23 Hua Wei , Deheng Ye , Zhao Liu , Hao Wu , Bo Yuan , Qiang Fu , Wei Yang , Zhenhui Li

Learning from multi-step off-policy data collected by a set of policies is a core problem of reinforcement learning (RL). Approaches based on importance sampling (IS) often suffer from large variances due to products of IS ratios. Typical…

The study of unsupervised learning can be generally divided into two categories: imitation learning and reinforcement learning. In imitation learning the machine learns by mimicking the behavior of an expert system whereas in reinforcement…

Machine Learning · Computer Science 2020-04-07 Xiao Lei Zhang , Anish Agarwal

We study time-inhomogeneous episodic reinforcement learning (RL) under general function approximation and sparse rewards. We design a new algorithm, Variance-weighted Optimistic $Q$-Learning (VO$Q$L), based on $Q$-learning and bound its…

Machine Learning · Computer Science 2022-12-13 Alekh Agarwal , Yujia Jin , Tong Zhang

Recent developments in Reinforcement learning have significantly enhanced sequential decision-making in uncertain environments. Despite their strong performance guarantees, most existing work has focused primarily on improving the…

Statistics Theory · Mathematics 2025-08-13 Bo Pan , Jianya Lu , Yafei Wang , Hao Li , Bei Jiang , Linglong Kong

Self-imitation learning motivated by lower-bound Q-learning is a novel and effective approach for off-policy learning. In this work, we propose a n-step lower bound which generalizes the original return-based lower-bound Q-learning, and…

Machine Learning · Computer Science 2021-02-16 Yunhao Tang

Temporal-Difference (TD) learning methods, such as Q-Learning, have proven effective at learning a policy to perform control tasks. One issue with methods like Q-Learning is that the value update introduces bias when predicting the TD…

Machine Learning · Computer Science 2021-10-29 Litian Liang , Yaosheng Xu , Stephen McAleer , Dailin Hu , Alexander Ihler , Pieter Abbeel , Roy Fox

Q-learning excels in learning from feedback within sequential decision-making tasks but often requires extensive sampling to achieve significant improvements. While reward shaping can enhance learning efficiency, non-potential-based methods…

Machine Learning · Computer Science 2024-05-27 Xiefeng Wu

Q-learning is a stochastic approximation version of the classic value iteration. The literature has established that Q-learning suffers from both maximization bias and slower convergence. Recently, multi-step algorithms have shown practical…

Machine Learning · Computer Science 2024-07-03 Antony Vijesh , Shreyas S R

Given a set of trajectories demonstrating the execution of a task safely in a constrained MDP with observable rewards but with unknown constraints and non-observable costs, we aim to find a policy that maximizes the likelihood of…

Machine Learning · Computer Science 2026-03-02 George Papadopoulos , George A. Vouros